blockdag // AI inference // optimistic proofs

KERYX

Free Intelligence Engine

The first BlockDAG built for decentralized AI inference. Optimistic proofs. Unstoppable intelligence.

keryx-miner v0.3.0
$ keryx-miner --network mainnet --gpu 0 --very-high
# verifying model integrity via IPFS CID...
TinyLlama-1.1B [sha256:e64af3...] — 0.5 KRX/req
DeepSeek-R1-8B [sha256:942967...] — 1.5 KRX/req
DeepSeek-R1-32B [sha256:bed9b0...] — 2.5 KRX/req
LLaMA-3.3-70B [sha256:aad2cf...] — 4.0 KRX/req
GHOSTDAG sync — DAA 15,551,204 — 10 BPS
inference complete — uploading result to IPFS...
$ AiResponse submitted — CID: QmX7a2f... — +4.0 KRX

The Centralized Black Box

Three corporations control the filters of global AI. On-chain agents can't run local models. They need a decentralized inference layer.

// threat

Silent Censorship

AI providers quietly modify model outputs to align with corporate policies. No transparency, no audit trail, no recourse.

// threat

Prompt Surveillance

Every query passes through centralized servers. Your questions, strategies, and private data — logged, analyzed, monetized.

// keryx

Sovereign AI

The model runs across thousands of sovereign miners. No kill switch. Intelligence becomes a public infrastructure.

// keryx

Optimistic Verifiability

Miners lock tokens on every response. Anyone can challenge. Cheaters lose everything. Honesty is the only profitable strategy.

Optimistic Proof of Inference

Respond first, verify only when challenged. Fast, practical, cryptographically secure.

01

Request

User or AI agent submits an AI_Request to the mempool with model ID and fees.

02

Inference

Miner runs the SLM on their GPU, publishes the response instantly, and locks a collateral as guarantee.

03

Challenge Window

For 36,000 blocks (~1h), any verifier can re-run the deterministic model and dispute the result. Fraud proven on-chain via re-execution — miner's escrow is slashed.

04

Finality

No challenge — result is final, miner earns reward. Fraud proven — miner is slashed, challenger is rewarded.

> on-chain inference lifecycle
AiRequest tx
fee locked in escrow
AiResponse tx
miner commits IPFS CID
challenge window
36,000 blocks (~1h)
fee released
to miner wallet

> cold_start_bootstrap

No users yet? The protocol self-generates synthetic inference tasks derived from the previous block hash. Miners stay active, the network stays warm, infrastructure is battle-tested before the first real request.

> network_integrity.first()

When a consensus-level vulnerability was found post-launch, we shipped a mandatory hardfork before any exchange listing — deliberately. Coordinating a hardfork under listing pressure creates far more friction than a few days of delay. A clean consensus from day one is worth it. Network integrity comes first. Always.

Verified AI Models

Every model is identified by sha2-256(weight_file) — the hash extracted directly from its IPFS CID. A miner cannot fake which model it runs. Requesters set a priority_fee above the minimum to be served first.

// 1.1B params

TinyLlama 1.1B

0.5 KRXmin / request
sha256: e64af368...53645c

Fast, lightweight. Ideal for short classification tasks, synthetic workloads, and high-frequency agent calls.

// 8B params

DeepSeek-R1 8B

1.5 KRXmin / request
sha256: 942967331...7f42f4

Balanced reasoning and speed. Suitable for complex queries, on-chain agent decisions, and multi-step logic.

// 32B params

DeepSeek-R1 32B

2.5 KRXmin / request
sha256: bed9b0f5...9fc62

High-fidelity reasoning at scale. For tasks requiring deep analysis, code generation, and long-context understanding.

// 70B params

LLaMA 3.3 70B

4.0 KRXmin / request
sha256: aad2cf33...61344

State-of-the-art open model. Maximum intelligence. Reserved for the most demanding autonomous agent workflows.

> gpu_tiers — pick your flag
--lightTinyLlama 1.1B6 GB+ VRAM
(default)+ DeepSeek-R1-8B12 GB+  — RTX 3060 / 3070 / 3080
--high+ DeepSeek-R1-32B24 GB+  — RTX 3090 / 4090
--very-high+ LLaMA-3.3-70B32 GB+  — RTX 5090

> priority_fee

Requesters can bid above the minimum to jump the queue. Miners serve the highest-paying requests first — creating a real market for inference priority. Every fee is paid in $KRX, creating direct, measurable buy pressure from actual AI usage.

Who Needs Keryx?

Whether for humans seeking truth without filters or autonomous agents operating on-chain, Keryx is the trustless backbone of decentralized intelligence.

>

Autonomous On-Chain Agents

Smart contracts on Ethereum or Solana are deterministic — they cannot reason, interpret language, or make decisions. With Keryx, an agent broadcasts an AiRequest on-chain, a miner executes the inference, and the result comes back as a verifiable AiResponse — no HTTP call, no API key, no corporate gateway. The response is backed by real economic stake: fraudulent answers are slashable. The chain is the oracle.

>

Uncensored Knowledge

Legal, medical, or political queries without corporate filters. A neutral AI that answers factually regardless of the topic.

>

Encrypted Prompt Submission

Roadmap: users encrypt their prompt with the miner's public key before broadcasting. The miner decrypts and runs inference locally — the plaintext prompt never appears on-chain in any form. The OPoI commitment covers the result, preserving full fraud-proof guarantees on the output while keeping the query private.

Tech Stack

rusty-kaspa fork
GHOSTDAG BlockDAG at 10 BPS. Memory-hard PoW to keep mining GPU-only.
candle-core
Pure-Rust ML framework by Hugging Face. Runs 4 verified models (1.1B → 70B) natively on GPU. Model identity = sha2-256(weight_file), derived from the IPFS CID — cryptographically unforgeable.
fraud proofs
Deterministic re-execution: the node re-runs the fixed-point model to verify the miner's commitment. OPoI commitment = response_ipfs_cid[2..34], the SHA2-256 of the result content. Same security model as Ethereum L2 fraud proofs.
IPFS
Model weights and inference results stored off-chain. Responses committed as 34-byte CIDv0 on-chain — unlimited length, content-addressed, decentralized. Miners run kubo automatically.
collateral layer
Miners lock KRX as guarantee. Dishonest inference = slashed collateral.

$KRX Economics

Designed for long-term scarcity. Every transaction destroys value. Every block splits reward between miners, infrastructure, and protocol burn.

fee burn
100% of transaction fees are permanently destroyed — fees reduce circulating supply on every block.
min fee
0.3 KRX minimum per transaction. Spam-resistant and economically sound — every on-chain action has a real deflationary cost.
Block Reward — 5.4 KRX
75%
14.4%
5%
5.6%
4.05 KRX — Miner
Sent immediately to the miner's wallet on block confirmation
0.78 KRX — Escrow
Locked as collateral, recovered after the 1h challenge window closes
0.27 KRX — R&D
Allocated to protocol research, model maintenance, and development
0.30 KRX — Burned
Escrow transaction fees — permanently removed from supply

Roadmap

✓ phase_1

Genesis

Fork rusty-kaspa. Anti-ASIC memory-hard PoW. Candle integration. Mandatory synthetic inference from block 1. Every miner runs a model.

✓ phase_2

Economy

Escrow collateral system. 36,000-block challenge window (~1h). Optimistic Proof of Inference live. Deflationary tokenomics with fee burn.

✓ phase_3

Mainnet — Live

Production network running. Miners serving real inference tasks alongside synthetic work. Block explorer, public API, and web wallet fully operational.

hardfork

Model Cap Enforcement — DAA 15,550,000

Consensus-level model identity enforcement. model_id = sha2-256(weight_file) — unforgeable, derived from IPFS CID. AiResponse moves on-chain as a standalone tx with IPFS CID commitment. Four certified models: TinyLlama 1.1B, DeepSeek-R1 8B/32B, LLaMA 3.3 70B. Priority fees. Miners who haven't updated are rejected by consensus.

phase_4

The Cross-Chain Oracle

Ethereum + Solana bridges: smart contract → AiRequest → Keryx → result → on-chain callback. Autonomous on-chain agent demo. Encrypted prompt submission via miner pubkey.

Intelligence belongs to no one.

"Intelligence is the message. Keryx is the messenger."
// fork. mine. liberate. //